repowisepriivacy-ai/spec-kitty

priivacy-ai / spec-kitty

★ 1,672
Use in your agentAsk this codebase

github.com/priivacy-ai/spec-kittyIndexed at bfcaf20Up to date with upstream

What is spec-kitty?

spec-kitty is a command-line tool for spec-driven development with AI coding agents. It turns product intent into a repeatable workflow of specifications, plans, tasks, actions, reviews, acceptance, and merging while storing context in the repository. The project is implemented as a Python CLI package.

Written by a model from the README and the source

Start reading

Code health

Health scores land with the first index: complexity, duplication, coverage, churn and ownership across every file.

Use priivacy-ai/spec-kitty in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/priivacy-ai/spec-kitty
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is spec-kitty put together?")
  • get_why("why is spec-kitty structured this way?")

Explore spec-kitty

Key features of spec-kitty

  • Spec Kitty provides guided specify, plan, and tasks workflows for starting from product intent.
  • Spec Kitty stores mission artifacts in the repository under kitty-specs/.
  • Spec Kitty divides implementation into work packages with lifecycle lanes such as planned, in_progress, for_review, and done.
  • Spec Kitty uses isolated Git worktrees under .worktrees/ to avoid branch switching during implementation.
  • Spec Kitty provides an optional local kanban dashboard through spec-kitty dashboard.
  • Spec Kitty integrates with common AI coding tools through slash commands or skills.

How priivacy-ai/spec-kitty works

spec-kitty starts with guided intent, planning, and task workflows that create repository-native artifacts under kitty-specs/. Work packages move through lifecycle lanes such as planned, in_progress, for_review, and done. Git worktrees under .worktrees/ isolate implementation work from branch switching. The spec-kitty command-line entry points coordinate actions such as initialization, setup verification, selecting the next task, dashboard access, upgrades, review, acceptance, and merging. Slash commands or skills connect common AI coding tools to the workflow. The tests directory validates the implementation, while docs and architecture provide project documentation and design material.

Getting started with spec-kitty

  1. Install the CLI with pipx.
    pipx install spec-kitty-cli
  2. Create or initialize a project, enter it, and verify the setup.
    spec-kitty init my-project --ai claude

Commands copied from the README

priivacy-ai/spec-kitty FAQ

What is spec-kitty?

spec-kitty is a command-line tool for spec-driven development with AI coding agents. It turns product intent into repository-based specifications, plans, tasks, reviews, and merge state.

How does spec-kitty work?

spec-kitty guides work from specification through planning, tasks, next actions, review, acceptance, and merging. It stores artifacts in kitty-specs/ and uses Git worktrees under .worktrees/ for isolated implementation.

How do I install spec-kitty?

spec-kitty can be installed with pipx install spec-kitty-cli. Supported alternatives include uv tool install spec-kitty-cli and python -m pip install spec-kitty-cli inside an activated virtual environment.

What language is spec-kitty written in?

spec-kitty is written in Python. The project provides a Python command-line interface.

How is the spec-kitty code organized?

spec-kitty is organized into src, kitty-specs, tests, architecture, docs, .kittify, scripts, and .github. The src directory holds the implementation, while tests, documentation, architecture material, and project templates support it.

Who is spec-kitty for?

spec-kitty is for teams and developers using AI coding agents who need requirements, decisions, acceptance criteria, work packages, and merge state kept in a Git repository. It supports multiple agents or developers with clear work package boundaries.

What license does spec-kitty use?

spec-kitty uses the MIT license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of priivacy-ai/spec-kitty from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.